Skip to content
Agentmart
Submit a tool

Aidimag

Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.

Connector by AiDimag · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/aidimag-aidimag

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools
13 read · 6 write · 1 delete · 1 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Node.js package

Tools by what they do 21

Read from the source code; the running server may list different tools.

Read 13 · Look things up without changing anything.

  • aidimag_help
  • chat_harvest
  • context_note
  • knowledge_pending
  • memory_check_change
  • memory_critique
  • memory_get_for_files
  • memory_search
  • memory_status
  • memory_verify
  • proposals_pending
  • scratchpad_read
Show 1 more tools
  • ticket_get

Write 6 · Create, change, send or run things.

  • commits_mine
  • knowledge_ingest_submit
  • memory_pre_edit
  • memory_refute
  • memory_write
  • scratchpad_write

Delete 1 · Delete, drop, revoke or wipe things.

  • scratchpad_clear

Not yet classified 1 · We could not tell from the name and description.

  • memory_propose

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • OPENAI_API_KEY

Other settings (environment variables or headers).

  • AIDIMAG_LLM
  • AIDIMAG_REPO

Network hosts it talks to 33

  • accounts.google.com · found in code
  • acme.atlassian.net · found in code
  • acme.youtrack.cloud · found in code
  • aidimag.com · found in code
  • api.app.shortcut.com · found in code
  • api.clickup.com · found in code
  • api.github.com · found in code
  • api.iconify.design · found in code
  • api.linear.app · found in code
  • api.notion.com · found in code
  • api.openai.com · found in code
  • api.trello.com · found in code
  • app.asana.com · found in code
  • app.clickup.com · found in code
  • app.shortcut.com · found in code
  • asana.com · found in code
  • cdn.jsdelivr.net · found in code
  • cloud.aidimag.com · found in code
  • dev.azure.com · found in code
  • fonts.googleapis.com · found in code
  • fonts.gstatic.com · found in code
  • github.com · found in code
  • gitlab.com · found in code
  • glama.ai · found in code
  • googletagmanager.com · found in code
  • id.atlassian.com · found in code
  • jetbrains.com · found in code
  • linear.app · found in code
  • notion.so · found in code
  • ollama.com · found in code
Show 3 more hosts
  • pivotaltracker.com · found in code
  • tickets.internal.acme.com · found in code
  • trello.com · found in code

Files it touches

  • /dev/null
  • /opt/homebrew/bin/ollama
  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (21)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • aidimag_help

    Show what aidimag offers: available tools, prompts (slash commands), resources, and the companion `dim` CLI commands. Call this when the user asks what aidimag can do, how to use it, or types 'aidimag help' — then relay the overview to them.

  • chat_harvest

    Harvest the CURRENT chat session on the fly: pass the messages the USER typed this session (verbatim) and durable facts are extracted and queued for human review — the live, tool-agnostic equivalent of `dim harvest`. Works from ANY IDE/agent (Copilot, Cursor, Codex, Claude, Devin, …), including cloud tools with no local transcripts. Call at session end, or after a long exchange rich in project knowledge. Secrets are redacted server-side before any LLM sees the text. For single facts stated in passing, prefer context_note instead.

  • commits_mine

    Mine git commit history for memory-worthy candidates (same as `dim mine`). Queues proposals for `dim review` — never writes active memory directly. Use after meaningful commits, or with full=true to rescan all history.

  • context_note

    Capture a durable fact the USER just stated in chat. Call this IMMEDIATELY when the user shares codebase knowledge — don't wait for session end. ALWAYS trigger on: 'we use X because Y' (DECISION), 'never do X' (GUARDRAIL), 'we always X' (CONVENTION), 'we tried X, it failed' (FAILED_APPROACH), 'the architecture is...' (ARCHITECTURE). Skip task-specific requests like 'fix this bug'. User-stated facts are queued for review with high trust (HUMAN_ATTESTED evidence).

  • knowledge_ingest_submit

    Submit the FALSIFIABLE claims you extracted from a pending knowledge doc (see the knowledge_ingest prompt). Queues them as proposals (source knowledge:<doc>), writes the durable summary, backs up the original, and clears the inbox copy. Claims become PINNED memory only after `dim review` (unless the repo opted out).

  • knowledge_pending

    List documents waiting in the knowledge inbox to be summarized into pinned-on-approve memory proposals. Use with the knowledge_ingest prompt to process them in-session.

  • memory_check_change

    Pre-edit safety check: given a diff or a short description of a change you're about to make, return any FAILED_APPROACH, GUARDRAIL, INVARIANT, or CONVENTION memories that match. Call this BEFORE editing code when the task touches an area with known historical failures or explicit rules. Returns a decision: proceed, ask_first, or stop.

  • memory_critique

    Review what you just did (or plan to do) against the project's VERIFIED memory and guardrails — a 'second critic' grounded in real, falsifiable beliefs rather than another model's opinion. Call BEFORE committing or proposing memories. Resolve guardrail violations and contradictions first.

  • memory_get_for_files

    Get all memories relevant to specific files before editing them — conventions, gotchas, and invariants that apply to those paths.

  • memory_pre_edit

    Pre-edit guardrail check for a specific file and code snippet. Given a file path and the code you're about to write, check whether it violates any NEVER guardrails or triggers FAILED_APPROACH warnings. Returns a clear STOP/PROCEED decision. Call this before writing to files in protected areas.

  • memory_propose

    Propose a memory for the human review queue. Use at SESSION END for learnings that should persist but warrant review before becoming active memory. Prefer this over memory_write for inferred/uncertain knowledge.

  • memory_refute

    Mark a memory as REFUTED when you discover it no longer holds. Optionally provide the id of a new memory that supersedes it. Refuted memories are kept as negative knowledge.

  • memory_search

    Search the repo's verified memory for decisions, conventions, gotchas, failed approaches, and invariants. Use BEFORE exploring the codebase — past sessions may already know the answer.

  • memory_status

    Get a summary of the repo's memory store: counts by verification status and kind.

  • memory_verify

    Re-run cheap evidence checks (STATIC_CHECK, COMMIT_REF) and update memory statuses. Use before relying on VERIFIED memories if the repo may have changed, or to verify specific memories by id.

Show 6 more tools
  • memory_write

    Persist a new memory about this codebase. Write the claim as a FALSIFIABLE statement (something that could be checked against the code). Attach evidence whenever possible. For kind=GUARDRAIL, set guardrail_level (never|always|ask-first).

  • proposals_pending

    List memory proposals awaiting human review.

  • scratchpad_clear

    Clear scratchpad working notes (one session key, or everything). Use when a task completes and its intermediate state is no longer needed.

  • scratchpad_read

    Read short-term working notes from the current session's scratchpad (newest first). Use at session start or when resuming a task to recover in-flight state. Expired notes are purged automatically.

  • scratchpad_write

    Jot a SHORT-TERM working note for the current session: intermediate findings, plans, hypotheses, task state. Auto-expires (default 24h) and is never synced. NOT durable memory — use memory_write/memory_propose for knowledge that should persist across sessions.

  • ticket_get

    Fetch the ticket behind the current work (title, description, type, status) from the connected ticketing app. Use at session end: the ticket carries the WHY that commits lack. Omit the id to auto-detect it from the current branch name.

Signals

Stars
1
Forks
0
Open issues
0
Last commit
Oct 8, 2026 (21 days ago)
Last release
Oct 8, 2026 (21 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.AiDimag/aidimag
Version
1.0.22
Auth
API key
Packages
npm aidimag
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Cite this page

Aidimag MCP server. Agent Mart. https://agentmart.dev/connectors/aidimag-aidimag (last updated 2026-10-25)